English
Related papers

Related papers: Stabilizing Transformer Training Through Consensus

200 papers

Multimodal learning systems often face substantial uncertainty due to noisy data, low-quality labels, and heterogeneous modality characteristics. These issues become especially critical in human-computer interaction settings, where data…

Artificial Intelligence · Computer Science 2025-11-21 Hyo-Jeong Jang

The main challenge that sets transfer learning apart from traditional supervised learning is the distribution shift, reflected as the shift between the source and target models and that between the marginal covariate distributions. In this…

Machine Learning · Statistics 2024-04-02 Zelin He , Ying Sun , Jingyuan Liu , Runze Li

Recurrent neural networks have been extensively studied in the context of neuroscience and machine learning due to their ability to implement complex computations. While substantial progress in designing effective learning algorithms has…

Neurons and Cognition · Quantitative Biology 2019-01-21 Francesca Mastrogiuseppe , Srdjan Ostojic

Diffusion models (DMs) are a powerful generative framework that have attracted significant attention in recent years. However, the high computational cost of training DMs limits their practical applications. In this paper, we start with a…

Machine Learning · Computer Science 2024-04-12 Tianshuo Xu , Peng Mi , Ruilin Wang , Yingcong Chen

Transfer learning is a simple and powerful method that can be used to boost model performance of low-resource neural machine translation (NMT). Existing transfer learning methods for NMT are static, which simply transfer knowledge from a…

Computation and Language · Computer Science 2022-12-09 Zhaocong Li , Xuebo Liu , Derek F. Wong , Lidia S. Chao , Min Zhang

This paper introduces a high-order Markov chain task to investigate how transformers learn to integrate information from multiple past positions with varying statistical significance. We demonstrate that transformers learn this task…

Machine Learning · Computer Science 2026-02-24 Oğuz Kaan Yüksel , Rodrigo Alvarez Lucendo , Nicolas Flammarion

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of…

Machine Learning · Computer Science 2020-11-12 Jisoo Lee , Sae-Young Chung

Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge…

Machine Learning · Computer Science 2022-09-23 James Harrison , Luke Metz , Jascha Sohl-Dickstein

Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers with hardmax self-attention and normalization sublayers as…

Computation and Language · Computer Science 2026-05-14 Albert Alcalde , Giovanni Fantuzzi , Enrique Zuazua

Recent advances in Transformer architectures have empowered their empirical success in a variety of tasks across different domains. However, existing works mainly focus on predictive accuracy and computational cost, without considering…

Machine Learning · Computer Science 2023-11-09 Xing Han , Tongzheng Ren , Tan Minh Nguyen , Khai Nguyen , Joydeep Ghosh , Nhat Ho

Deep learning systems achieve remarkable empirical performance, yet the stability of the training process itself remains poorly understood. Training unfolds as a high-dimensional dynamical system in which small perturbations to…

Machine Learning · Computer Science 2026-01-21 Zhipeng Zhang , Zhenjie Yao , Kai Li , Lei Yang

In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Sheng-Kai Huang , Jiun-Feng Chang , Chun-Rong Huang

The aim of this paper is to analyze a class of consensus algorithms with finite-time or fixed-time convergence for dynamic networks formed by agents with first-order dynamics. In particular, in the analyzed class a single evaluation of a…

Training Memory-based transformers can require a large amount of memory and can be quite inefficient. We propose a novel two-phase training mechanism and a novel regularization technique to improve the training efficiency of memory-based…

Machine Learning · Computer Science 2023-11-15 Vishwajit Kumar Vishnu , C. Chandra Sekhar

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

Machine Learning · Computer Science 2024-03-06 Suzan Ece Ada , Emre Ugur , H. Levent Akin

The objective of this paper is to enhance the optimization process for neural networks by developing a dynamic learning rate algorithm that effectively integrates exponential decay and advanced anti-overfitting strategies. Our primary…

Machine Learning · Computer Science 2025-08-04 Jatin Chaudhary , Dipak Nidhi , Jukka Heikkonen , Haari Merisaari , Rajiv Kanth

We present here an introduction to Brainstorming approach, that was recently proposed as a consensus meta-learning technique, and used in several practical applications in bioinformatics and chemoinformatics. The consensus learning denotes…

Machine Learning · Statistics 2016-09-08 Dariusz Plewczynski

We examine the stability of loss-minimizing training processes that are used for deep neural networks (DNN) and other classifiers. While a classifier is optimized during training through a so-called loss function, the performance of…

Analysis of PDEs · Mathematics 2020-10-05 Leonid Berlyand , Pierre-Emmanuel Jabin , C. Alex Safsten

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras
‹ Prev 1 3 4 5 6 7 10 Next ›